© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 221277
    Prev
    Next
    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite

    academic and descriptive prose

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     outperforms
    0.50
     statistical
    0.47
     edge
    0.46
     datafile
    0.46
    5
    0.46
     overcast
    0.46
     golfers
    0.45
     DCP
    0.45
     rating
    0.45
     outperformed
    0.45
    POSITIVE LOGITS
    kirche
    0.54
    em
    0.51
    别墅
    0.48
    memb
    0.48
    them
    0.47
    ötzlich
    0.47
    ピアノ
    0.45
    quellen
    0.45
    雦
    0.45
    ując
    0.45
    Activations Density 0.001%

    No Known Activations